{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:25Z","timestamp":1774419805990,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890689","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models"],"prefix":"10.1109","author":[{"given":"Lala Shakti Swarup","family":"Ray","sequence":"first","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI),Germany"}]},{"given":"Bo","family":"Zhou","sequence":"additional","affiliation":[{"name":"RPTU Kaiserslautern-Landau,Department of Computer Science,Germany"}]},{"given":"Sungho","family":"Suh","sequence":"additional","affiliation":[{"name":"RPTU Kaiserslautern-Landau,Department of Computer Science,Germany"}]},{"given":"Paul","family":"Lukowicz","sequence":"additional","affiliation":[{"name":"RPTU Kaiserslautern-Landau,Department of Computer Science,Germany"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref2","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024"},{"key":"ref3","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International Conference on machine learning","author":"Li"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3441495"},{"key":"ref5","article-title":"Instruct2act: Mapping multi-modality instructions to robotic actions with large language model","author":"Huang","year":"2023"},{"key":"ref6","article-title":"Code llama: Open foundation models for code","author":"Roziere","year":"2023"},{"key":"ref7","article-title":"Codegen: An open large language model for code with multi-turn program synthesis","author":"Nijkamp","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops59983.2024.10503379"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01955"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/percom64205.2025.00020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78110-0_9"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8070-3_10"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8511-7_28"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FMSys62467.2024.00011"},{"key":"ref18","article-title":"Unsupervised human activity recognition through two-stage prompting with chatgpt","author":"Xia","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref20","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"ref21","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref22","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref23","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01754"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/c.24.50"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050642"},{"key":"ref30","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364921990671"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11839-0"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref34","article-title":"Caption anything: Interactive image description with diverse multimodal controls","author":"Wang","year":"2023"},{"key":"ref35","first-page":"38571","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Xu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref37","article-title":"Videollama 2: Advancing spatial-temporal modeling and audio understanding in video-llms","author":"Cheng","year":"2024"},{"key":"ref38","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890689.pdf?arnumber=10890689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:47Z","timestamp":1774416287000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890689","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}